* feat: persist webdav state
* feat: schedule autosync by taking the last autosync time
* fix: correct scheduling behaviour with last error, improve messages
* refactor: delay setting lastSyncTime
---------
Co-authored-by: 亢奋猫 <kangfenmao@qq.com>
* refactor: remove unused filterMCPTools function calls from providers
* fix: ensure enabledMCPs is checked for length before processing tools
* feat: implement caching for tools retrieved from MCP server
- Improve filterPropertieAttributes to handle nested object and array types, preserving their structure while filtering attributes.
- Make parameters optional when no properties exist. (Fix#3270)
- Modified the assistant deletion logic to check if the deleted assistant is the currently active one before updating the active assistant state. This prevents potential issues when the active assistant is removed.
- Added "advanced_settings" key to English, Japanese, Russian, Chinese, and Traditional Chinese localization files for better user experience.
- Corrected translations for "chunk_size" and "chunk_overlap" in Chinese and Traditional Chinese localization files to enhance clarity.
- Updated the file content extraction method to check for non-empty file arrays, enhancing the handling of messages with files.
- Replaced the previous check for `message.files` with a more robust check using `isEmpty` from lodash to ensure proper validation.
- Incremented the version of the persisted reducer from 80 to 81.
- Introduced a new constant `INITIAL_PROVIDERS` to define the initial state of LLM providers.
- Refactored migration functions to utilize `INITIAL_PROVIDERS` for adding providers to the state, improving maintainability and readability.
- Updated migration logic to ensure new providers are added correctly during state migrations.
* feat: support Github Copilot
* feat: finish i18n translate
* fix: add safeStorage
* clean code
* chore: remove vision model
* ✨ feat: add Model Context Protocol (MCP) support (#2809)
* ✨ feat: add Model Context Protocol (MCP) server configuration (main)
- Added `@modelcontextprotocol/sdk` dependency for MCP integration.
- Introduced MCP server configuration UI in settings with add, edit, delete, and activation functionalities.
- Created `useMCPServers` hook to manage MCP server state and actions.
- Added i18n support for MCP settings with translation keys.
- Integrated MCP settings into the application's settings navigation and routing.
- Implemented Redux state management for MCP servers.
- Updated `yarn.lock` with new dependencies and their resolutions.
* 🌟 feat: implement mcp service and integrate with ipc handlers
- Added `MCPService` class to manage Model Context Protocol servers.
- Implemented various handlers in `ipc.ts` for managing MCP servers including listing, adding, updating, deleting, and activating/deactivating servers.
- Integrated MCP related types into existing type declarations for consistency across the application.
- Updated `preload` to expose new MCP related APIs to the renderer process.
- Enhanced `MCPSettings` component to interact directly with the new MCP service for adding, updating, deleting servers and setting their active states.
- Introduced selectors in the MCP Redux slice for fetching active and all servers from the store.
- Moved MCP types to a centralized location in `@renderer/types` for reuse across different parts of the application.
* feat: enhance MCPService initialization to prevent recursive calls and improve error handling
* feat: enhance MCP integration by adding MCPTool type and updating related methods
* feat: implement streaming support for tool calls in OpenAIProvider and enhance message processing
* fix: finish_reason undefined
* fix migrate
* feat: add rate limit and warning
* feat: add delete copilot token file
feat: add login message
feat: add default headers and change getCopilotToken algorithm
* fix
* feat: add rate limit
* chore: change apihost
* fix: remove duplicate apikey
* fix: change api host
* chore: add vertify first tooltip
---------
Co-authored-by: 亢奋猫 <kangfenmao@qq.com>
Co-authored-by: LiuVaayne <10231735+vaayne@users.noreply.github.com>
* feat: Add search summary model and related functionality
- Introduce new search summary model configuration in settings
- Implement search summary prompt and model selection
- Add support for generating search keywords across providers
- Update localization files with new search summary model translations
- Enhance web search functionality with search summary generation
* refactor: Improve web search error handling and async flow
* fix: Update migration version for settings search summary prompt
* refactor(webSearch): Remove search summary model references from settings and localization files
- Deleted search summary model entries from English, Japanese, Russian, Chinese, and Traditional Chinese localization files.
- Refactored ModelSettings component to remove search summary model handling.
- Updated related services and settings to eliminate search summary model dependencies.
* refactor(llm): Remove search summary model from state and related hooks
- Replaced direct background color logic in Navbar and Sidebar components with useNavBackgroundColor hook for improved maintainability.
- Updated navbar background color variable in index.scss for consistency across components.
- Enhanced handling of background color based on window style and application state.
- Introduced isNameManuallyEdited property to the Topic type for better tracking of manual edits.
- Updated topic update logic to set isNameManuallyEdited based on user actions in the TopicsTab.
- Enhanced autoRenameTopic function to respect manual edits and prevent automatic renaming when applicable.
* feat: add support for citation preview
#3217
* feat(MessageContent): Add HTML entity encoding to enhance the security of quoted data
* fix(MessageContent): recognize citation format like `[[1]]`
- Introduced new translations for "Pasted Text" and "Pasted Image" in English, Japanese, Russian, Simplified Chinese, and Traditional Chinese.
- Updated FileManager to format file names based on their type, enhancing user experience when handling pasted content.
